arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2205.04762cs.LG
收藏

基于动态学习图卷积机制的短时交通流时空预测模型

A spatial-temporal short-term traffic flow prediction model based on dynamical-learning graph convolution mechanism

Wuhan University of Technology(武汉理工大学);Delft University of Technology(代尔夫特理工大学)

Zhijun Chen, Zhe Lu, Qiushi Chen, Hongliang Zhong, Yishi Zhang, Jie Xue, Chaozhong Wu

摘要:

短时交通流预测是智能交通系统(ITS)的一个重要分支,在交通管理中起着重要的作用。图卷积网络(GCN)被广泛应用于交通预测模型中,以更好地处理道路网络的图形结构数据。然而,在现实生活中,不同路段之间的影响权重往往是不同的,很难人工分析。传统的GCN机制依赖于人工设置邻接矩阵,无法在训练过程中动态学习这种空间模式。针对这一缺陷,提出了一种新的位置图卷积网络(Location-GCN)。位置GCN通过在GCN机制中添加一个新的可学习矩阵来解决这个问题,使用这个矩阵的绝对值来表示不同节点之间的不同影响水平。然后,长短期记忆(LSTM)的流量预测模型中使用。此外,三角函数编码是在这项研究中,使短期的输入序列传达长期的周期性信息。最后,该模型与基线模型进行了比较,并在两个真实的世界交通流数据集上进行了评估。结果表明,我们的模型是更准确和更强大的两个数据集上比其他代表性的交通预测模型。

英文摘要:

Short-term traffic flow prediction is a vital branch of the Intelligent Traffic System (ITS) and plays an important role in traffic management. Graph convolution network (GCN) is widely used in traffic prediction models to better deal with the graphical structure data of road networks. However, the influence weights among different road sections are usually distinct in real life, and hard to be manually analyzed. Traditional GCN mechanism, relying on manually-set adjacency matrix, is unable to dynamically learn such spatial pattern during the training. To deal with this drawback, this paper proposes a novel location graph convolutional network (Location-GCN). Location-GCN solves this problem by adding a new learnable matrix into the GCN mechanism, using the absolute value of this matrix to represent the distinct influence levels among different nodes. Then, long short-term memory (LSTM) is employed in the proposed traffic prediction model. Moreover, Trigonometric function encoding is used in this study to enable the short-term input sequence to convey the long-term periodical information. Ultimately, the proposed model is compared with the baseline models and evaluated on two real word traffic flow datasets. The results show our model is more accurate and robust on both datasets than other representative traffic prediction models.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑